论文标题
UNITE：统一翻译评估
UniTE: Unified Translation Evaluation
论文作者
论文摘要
翻译质量评估在机器翻译中起着至关重要的作用。根据输入格式，它主要分为三个任务，即仅参考，仅源和源引用兼而有之。尽管有希望的结果，但最近的方法是针对其中一种方法专门设计和优化的。这限制了这些方法的便利性，并忽略了任务之间的共同点。在本文中，我们提出了Unite，这是第一个具有处理所有三个评估任务的能力的统一框架。具体而言，我们提出了单调的区域关注，以控制输入段之间的相互作用，并预处理以更好地适应多任务学习。我们在WMT 2019指标和WMT 2020质量估计基准上作证了我们的框架。广泛的分析表明，我们的\ textit {单个模型}可以普遍超越任务跨任务的各种最新或赢家方法。源代码和关联模型均可在https://github.com/nlp2ct/unite上获得。
Translation quality evaluation plays a crucial role in machine translation. According to the input format, it is mainly separated into three tasks, i.e., reference-only, source-only and source-reference-combined. Recent methods, despite their promising results, are specifically designed and optimized on one of them. This limits the convenience of these methods, and overlooks the commonalities among tasks. In this paper, we propose UniTE, which is the first unified framework engaged with abilities to handle all three evaluation tasks. Concretely, we propose monotonic regional attention to control the interaction among input segments, and unified pretraining to better adapt multi-task learning. We testify our framework on WMT 2019 Metrics and WMT 2020 Quality Estimation benchmarks. Extensive analyses show that our \textit{single model} can universally surpass various state-of-the-art or winner methods across tasks. Both source code and associated models are available at https://github.com/NLP2CT/UniTE.
